Mercurial > hg > cc > cirrus_home
view src/nutch-cc/conf/nutch-site.xml @ 148:f0bee28995f1
do the work for cdx2sql
author | Henry S. Thompson <ht@inf.ed.ac.uk> |
---|---|
date | Mon, 25 Oct 2021 15:05:46 +0000 |
parents | b7daa4f8767c |
children |
line wrap: on
line source
<?xml version="1.0"?> <?xml-stylesheet type="text/xsl" href="configuration.xsl"?> <!-- Put site-specific property overrides in this file. --> <configuration> <!-- from email from Sebastian 2020-04-16, ccrawl:57[01] --> <property><name>http.content.limit</name><value>-1</value></property> <property><name>http.store.responsetime</name><value>true</value></property> <property><name>store.ip.address</name><value>true</value></property> <property><name>store.http.request</name><value>true</value></property> <property><name>store.http.headers</name><value>true</value></property> <property><name>http.accept.language</name><value>en-US,en;q=0.5</value></property> <property><name>http.accept.charset</name><value> </value></property> <property><name>http.time.limit</name><value>1200</value></property> <property><name>http.timeout</name><value>45000</value></property> <property><name>http.redirect.max</name><value>3</value></property> <property><name>http.redirect.max.skip</name><value>false</value></property> <property><name>http.partial.truncated</name><value>true</value></property> <!-- need to fill your crawler contact information --> <property><name>http.agent.name</name><value>htInEdin</value></property> <!--<property><name>http.robots.agents</name><value>XXX</value></property>--> <property><name>http.agent.description</name><value>Experimental PDF crawler</value></property> <property><name>http.agent.url</name><value>http://www.ltg.ed.ac.uk/~ht/pdfCrawl.html</value></property> <property><name>http.agent.version</name><value>0.1</value></property> <property><name>fetcher.store.content</name><value>false</value></property> <property><name>fetcher.store.robotstxt</name><value>true</value></property> <property><name>fetcher.store.404s</name><value>true</value></property> <property><name>fetcher.store.warc</name><value>true</value></property> <property><name>fetcher.signature</name><value>true</value></property> <property><name>fetcher.redirect.dedupcache.seconds</name><value>5400</value></property> <property><name>fetcher.redirect.dedupcache.size</name><value>6000</value></property> <property><name>fetcher.threads.timeout.divisor</name><value>1</value></property> <property><name>mapreduce.fileoutputcommitter.marksuccessfuljobs</name> <value>true</value></property> <property><name>mapreduce.task.timeout</name><value>1200000</value> <!-- from hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/target/classes/mapred-default.xml <value>600000</value> <description>The number of milliseconds before a task will be terminated if it neither reads an input, writes an output, nor updates its status string. A value of 0 disables the timeout. [HST thinks 0 caused an immediate thread termination when he tried it!] </description> --> </property> <!-- we use okhttp --> <property><name>plugin.includes</name><value>protocol-okhttp</value></property> <!-- WARC file names and info header - needs to be adapted, e.g. that's the info of the current March/April crawl: PREFIX=CC-MAIN ISPARTOF=CC-MAIN-2020-16 PUBLISHER='Common Crawl' OPERATOR='Common Crawl Admin (info@commoncrawl.org)' SOFTWARE='Apache Nutch 1.16 (modified, https://github.com/commoncrawl/nutch/)' DESCRIPTION='Wide crawl of the web for March/April 2020' --> <property><name>warc.export.prefix</name><value>CC-HST-PDF</value></property> <property><name>warc.export.operator</name><value>ht@inf.ed.ac.uk</value></property> <property><name>warc.export.publisher</name><value>School of Informatics, University of Edinburgh</value></property> <property><name>warc.export.software</name><value>Apache Nutch 1.16 (modified, https://github.com/commoncrawl/nutch/)</value></property> <property><name>warc.export.description</name><value>Augment CC of August 2020 with PDFs larger than 1MB</value></property> <!--property><name>warc.export.isPartOf</name><value>$ISPARTOF</value></property--> <!-- further WARC writer config --> <!-- trying relative paths??? --> <property><name>warc.export.path</name><value>warc</value></property> <property><name>warc.export.cdx.path</name><value>cdx</value></property> <property><name>warc.deduplicate</name><value>true</value></property> <property><name>warc.export.text</name><value>false</value></property> <property><name>warc.export.crawldiagnostics</name><value>true</value></property> <property><name>warc.export.robotstxt</name><value>true</value></property> <property><name>warc.export.cdx</name><value>true</value></property> </configuration>